Scribd Logo
Upload

Welcome to Scribd!

  • 3 views

    Solutions 8

    Uploaded by

    Ulya Rey
    This document provides solutions to problems related to advanced statistics. It includes calculating moment generating functions for different probability distributions, finding the MGF of a standardized Poisson random variable, and deriving the probability density function of a normal distribution from its cumulative distribution function.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    Solutions 8

    Uploaded by

    Ulya Rey
    3 views2 pages
    This document provides solutions to problems related to advanced statistics. It includes calculating moment generating functions for different probability distributions, finding the MGF of a standardized Poisson random variable, and deriving the probability density function of a normal distribution from its cumulative distribution function.

    Original Description:

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This document provides solutions to problems related to advanced statistics. It includes calculating moment generating functions for different probability distributions, finding the MGF of a standardized Poisson random variable, and deriving the probability density function of a normal distribution from its cumulative distribution function.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    3 views2 pages

    Solutions 8

    Uploaded by

    Ulya Rey
    This document provides solutions to problems related to advanced statistics. It includes calculating moment generating functions for different probability distributions, finding the MGF of a standardized Poisson random variable, and deriving the probability density function of a normal distribution from its cumulative distribution function.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 2

    Tutorial Advanced Statistics Winter Term 2023/24

    Solutions 8

    1. (a) MGF of binomial: MX (t) = (1 − p + pet )n with n = 1 ⇒ MX (t) = 1 − p + pet which


    is the MGF of a Bernoulli distribution.
    (b) MGF of a Gamma distribution: MX (t) = (1 − βt)−α with β = θ and α = 1 one gets
    MX (t) = (1 − θt)−1 which is the MGF of an exponential distribution.
    (c) Using the MGF of a Gamma distribution with β = 2 and α = ν2 one gets
    ν
    MX (t) = (1 − 2t)− 2 which is the MGF of a Chi squared distribution.
    (d) The MGF of a Beta distribution is
    ∞
    X B(r + α, β) tr
    MX (t) = 1 + with α = β = 1
    B(α, β) r!
    r=1
    ∞
    X B(r + 1, 1) tr
    =1+
    B(1, 1) r!
    r=1
    ∞
    X Γ(r + 1)Γ(1) Γ(2) tr
    =1+
    Γ(r + 2) Γ(1)Γ(1) r!
    r=1
    ∞ ∞
    X Γ(r + 1) tr X tr
    =1+ =1+ with k = r + 1
    (r + 1)Γ(r + 1) r! (r + 1)!
    r=1 r=1
    ∞ k−1 ∞
    "∞ #
    X t 1 X tk 1 X tk
    =1+ =1+ =1+ −t−1
    k! t k! t k!
    k=2 k=2 k=0
    1
    = (et − 1)
    t
    which is the MGF of a standard uniform distribution.
    t −1)
    (e) The MGF of a Poisson distributed random variable X is given by MX (t) = eλ(e .
    Define the "standardized" random variable Z = X−λ
    √ . The MGF of Z is
    λ

    √ √
     
     tZ  h X−λ
    t √
    i
    −t λ
    h √t i
    X −t λ t
    MZ (t) = E e =E e λ =e E e λ =e MX √
    λ
     
    √
        
    √ ∞ ζ
    t X t −ζ
    = e−t λ exp λ exp √ −1 = exp −t λ + λ λ 2 − λ
    λ ζ!
    ζ=0
       
    √ ∞ ζ ∞ ζ
    X t − ζ−2  X t − ζ−2 
    = exp −t λ +
     λ 2 = exp  λ 2
    ζ! ζ!
    ζ=1 ζ=2
     
    ∞
    t2 X tζ − ζ−2 
    = exp  + λ 2
    2 ζ!
    ζ=3
     2
    t
    lim MZ (t) = exp
    λ→∞ 2

    which is the MGF of a standard normal distributed random variable. Thus also X
    itself is normally distributed.

    1
    Tutorial Advanced Statistics Winter Term 2023/24

    2.
     
    MZ (t) = E et1 z1 +t2 z2 = E et1 (x1 +x2 )+t2 (x1 −x2 ) =
    
       
    = E ex1 (t1 +t2 )+x2 (t1 −t2 ) = E ex1 (t1 +t2 ) ex2 (t1 −t2 ) =
       
    = E ex1 (t1 +t2 ) E ex2 (t1 −t2 ) = MX1 (t1 + t2 )MX2 (t1 − t2 ) =
    λ λ λ2
    = · =
    λ − t1 − t2 λ − t1 + t2 (λ − t1 − t2 )(λ − t1 + t2 )

    3. (a)

    (ω − µ)2 ω 2 − 2µω + µ2
    Z   Z  
    tω tω 1 1 tω
    Mω (t) = E(e ) = e √ exp − dω = √ e exp − dω
    2πσ 2σ 2 2πσ 2σ 2
    ω 2 − 2ω(µ + tσ 2 ) + µ2
    Z  
    1
    = √ exp − dω
    2πσ 2σ 2
    ω 2 − 2ω(µ + tσ 2 ) + (µ + tσ 2 )2 − (µ + tσ 2 )2 + µ2
    Z  
    1
    = √ exp − dω
    2πσ 2σ 2
    (µ + tσ 2 )2 − µ2 (ω − µ − tσ 2 )2
    Z    
    1
    = exp √ exp − dω
    2σ 2 2πσ 2σ 2
    (µ + tσ 2 )2 − µ2
     2
    µ + 2µtσ 2 + t2 σ 4 − µ2
      
    = exp = exp
    2σ 2 2σ 2
     
    1
    = exp µt + t2 σ 2
    2

    (b)

    FX (x) = P (X ≤ x) = P (|ω| < x) = P (−x ≤ ω ≤ x) = P (ω ≤ x) − P (ω ≤ −x)


    = Φ(x) − Φ(−x)
    r
    ∂FX (x) 2 x2 2 − x2
    f (x) = = φ(x) + φ(−x) = 2φ(x) = √ e− 2 = e 2 I(0,∞) (x)
    ∂x 2π π

    You might also like